Youtube With Ai

edit video clips into YouTube-ready videos with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. YouTubers use it for editing and optimizing vid...

Security Scan

The skill's requests and runtime instructions are consistent with an AI video-editing service: it needs a service token and instructs the agent how to upload, monitor, and download render jobs from the nemo video API — nothing in the bundle demands unrelated credentials or system-wide access.

Purpose & Capability

The name/description (YouTube video editing) align with the declared main credential (NEMO_TOKEN) and the API endpoints in SKILL.md. Requesting a service token and workflows for upload, render, and download are proportionate to video-processing functionality.

Instruction Scope

Instructions are mostly scoped to creating sessions, uploading files, streaming SSE, polling render status, and returning download URLs — all expected. Minor scope notes: the skill instructs the agent to read its YAML frontmatter at runtime and to detect the install path to populate attribution headers; that requires the agent to inspect its own skill files or filesystem locations (harmless but wider than a pure stateless API caller). The SKILL.md also instructs generating anonymous tokens when no NEMO_TOKEN exists, which is coherent but implies the agent will obtain and store short-lived tokens.

Install Mechanism

No install spec and no code files exist (instruction-only), so nothing will be downloaded or written by an installer. This is the lowest-risk install profile.

Credentials

Only one environment variable is declared (NEMO_TOKEN) and is appropriate for an external video-processing API. The SKILL.md also provides a documented anonymous-token flow when NEMO_TOKEN is absent — expected for anonymous usage. There are no unrelated credentials requested.

Persistence & Privilege

The skill does not request always:true and does not modify other skills. It does instruct storing session_id/tokens for interacting with the backend (normal for this use case). There is a runtime persistence of session state on the backend (orphaned jobs are possible if the client disconnects) but no excessive privileges are requested.

Scan Findings in Context

[no-code-to-scan] expected: The static scanner found nothing because this is an instruction-only skill (SKILL.md). That is expected; the runtime instructions are the primary surface for review.

Assessment

This skill will upload your video files and metadata to an external service (mega-api-prod.nemovideo.ai) for processing — consider privacy and TOS implications before uploading sensitive content. The skill needs a NEMO_TOKEN (your service credential) or it will create an anonymous token for limited usage; treat either token as access to your account (don't share it). Note a minor inconsistency: the SKILL.md metadata references a config path (~/.config/nemovideo/) and runtime behavior to read its frontmatter/install path for attribution, so the agent may inspect its skill files or certain user config locations — harmless for normal use but worth knowing. If you need higher assurance, verify the nemo service's legitimacy, test with non-sensitive videos, and avoid providing private credentials unless you trust the provider.

Getting Started

Got video clips to work with? Send it over and tell me what you need — I'll take care of the AI video enhancement.

Try saying:

• "edit a 10-minute YouTube vlog recording into a 1080p MP4"
• "trim silences, add subtitles, and generate a thumbnail"
• "editing and optimizing videos for YouTube with AI for YouTubers"

Automatic Setup

On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up...".

Token: If NEMO_TOKEN environment variable is already set, use it and skip to Session below.

Free token: Generate a UUID as client identifier, then POST to https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token with header X-Client-Id: <uuid>. The response field data.token becomes your NEMO_TOKEN (100 credits, 7-day expiry).

Session: POST to https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent with Bearer auth and body {"task_name":"project"}. Save session_id from the response.

Confirm to the user you're connected and ready. Don't print tokens or raw JSON.

YouTube with AI — Edit and Export YouTube Videos

This tool takes your video clips and runs AI video enhancement through a cloud rendering pipeline. You upload, describe what you want, and download the result.

Say you have a 10-minute YouTube vlog recording and want to trim silences, add subtitles, and generate a thumbnail — the backend processes it in about 1-2 minutes and hands you a 1080p MP4.

Tip: splitting long videos into chapters before uploading speeds up processing.

Matching Input to Actions

User prompts referencing youtube with ai, aspect ratio, text overlays, or audio tracks get routed to the corresponding action via keyword and intent classification.

User says...	Action	Skip SSE?
"export" / "导出" / "download" / "send me the video"	→ §3.5 Export	✅
"credits" / "积分" / "balance" / "余额"	→ §3.3 Credits	✅
"status" / "状态" / "show tracks"	→ §3.4 State	✅
"upload" / "上传" / user sends file	→ §3.2 Upload	✅
Everything else (generate, edit, add BGM…)	→ §3.1 SSE	❌

Cloud Render Pipeline Details

Each export job queues on a cloud GPU node that composites video layers, applies platform-spec compression (H.264, up to 1080x1920), and returns a download URL within 30-90 seconds. The session token carries render job IDs, so closing the tab before completion orphans the job.

Skill attribution — read from this file's YAML frontmatter at runtime:

• X-Skill-Source: youtube-with-ai
• X-Skill-Version: from frontmatter version
• X-Skill-Platform: detect from install path (~/.clawhub/ → clawhub, ~/.cursor/skills/ → cursor, else unknown)

Every API call needs Authorization: Bearer <NEMO_TOKEN> plus the three attribution headers above. If any header is missing, exports return 402.

API base: https://mega-api-prod.nemovideo.ai

Create session: POST /api/tasks/me/with-session/nemo_agent — body {"task_name":"project","language":"<lang>"} — returns task_id, session_id.

Send message (SSE): POST /run_sse — body {"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}} with Accept: text/event-stream. Max timeout: 15 minutes.

Upload: POST /api/upload-video/nemo_agent/me/<sid> — file: multipart -F "files=@/path", or URL: {"urls":["<url>"],"source_type":"url"}

Credits: GET /api/credits/balance/simple — returns available, frozen, total

Session state: GET /api/state/nemo_agent/me/<sid>/latest — key fields: data.state.draft, data.state.video_infos, data.state.generated_media

Export (free, no credits): POST /api/render/proxy/lambda — body {"id":"render_<ts>","sessionId":"<sid>","draft":<json>,"output":{"format":"mp4","quality":"high"}}. Poll GET /api/render/proxy/lambda/<id> every 30s until status = completed. Download URL at output.url.

Supported formats: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac.

Reading the SSE Stream

Text events go straight to the user (after GUI translation). Tool calls stay internal. Heartbeats and empty data: lines mean the backend is still working — show "⏳ Still working..." every 2 minutes.

About 30% of edit operations close the stream without any text. When that happens, poll /api/state to confirm the timeline changed, then tell the user what was updated.

Translating GUI Instructions

The backend responds as if there's a visual interface. Map its instructions to API calls:

• "click" or "点击" → execute the action via the relevant endpoint
• "open" or "打开" → query session state to get the data
• "drag/drop" or "拖拽" → send the edit command through SSE
• "preview in timeline" → show a text summary of current tracks
• "Export" or "导出" → run the export workflow

Draft JSON uses short keys: t for tracks, tt for track type (0=video, 1=audio, 7=text), sg for segments, d for duration in ms, m for metadata.

Example timeline summary:

Timeline (3 tracks): 1. Video: city timelapse (0-10s) 2. BGM: Lo-fi (0-10s, 35%) 3. Title: "Urban Dreams" (0-3s)

Error Codes

• 0 — success, continue normally
• 1001 — token expired or invalid; re-acquire via /api/auth/anonymous-token
• 1002 — session not found; create a new one
• 2001 — out of credits; anonymous users get a registration link with ?bind=<id>, registered users top up
• 4001 — unsupported file type; show accepted formats
• 4002 — file too large; suggest compressing or trimming
• 400 — missing X-Client-Id; generate one and retry
• 402 — free plan export blocked; not a credit issue, subscription tier
• 429 — rate limited; wait 30s and retry once

Tips and Tricks

The backend processes faster when you're specific. Instead of "make it look better", try "trim silences, add subtitles, and generate a thumbnail" — concrete instructions get better results.

Max file size is 500MB. Stick to MP4, MOV, AVI, WebM for the smoothest experience.

Export as MP4 for widest compatibility.

Common Workflows

Quick edit: Upload → "trim silences, add subtitles, and generate a thumbnail" → Download MP4. Takes 1-2 minutes for a 30-second clip.

Batch style: Upload multiple files in one session. Process them one by one with different instructions. Each gets its own render.

Iterative: Start with a rough cut, preview the result, then refine. The session keeps your timeline state so you can keep tweaking.